{"id":"W4389272161","doi":"10.1007/978-3-031-47966-3_14","title":"Regularized Meta-Training with Embedding Mixup for Improved Few-Shot Learning","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Embedding; Computer science; Generalization; Artificial intelligence; Regularization (linguistics); Machine learning; Metric (unit); Shot (pellet); Set (abstract data type); Training set; Domain (mathematical analysis); GRASP; One shot; Range (aeronautics); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002654826,0.0008160163,0.001168453,0.001168409,0.0008934743,0.001277097,0.002769034,0.0003746317,0.00002806609],"category_scores_gemma":[0.000489724,0.0006809567,0.0003878158,0.001085345,0.00060547,0.0008188266,0.0008897978,0.001414753,0.00003299258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002267611,"about_ca_system_score_gemma":0.0007644909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001147698,"about_ca_topic_score_gemma":0.00005641521,"domain_scores_codex":[0.9947221,0.00008975364,0.0007303903,0.002242476,0.001020247,0.00119504],"domain_scores_gemma":[0.9957452,0.001748549,0.0006467474,0.001145137,0.0004323518,0.000282057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006388452,0.0000228435,0.000008667208,0.0001079248,0.0004035777,0.0001028028,0.00581629,0.3304143,0.001565656,0.05374116,0.00002599594,0.6077269],"study_design_scores_gemma":[0.0008371618,0.0003873808,0.00001539482,0.0002742389,0.0001187839,0.00006308146,0.000004867838,0.9515267,0.0003127614,0.03962925,0.005877062,0.0009532977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000238048,0.0001637129,0.9937816,0.001173312,0.001216655,0.0008288608,0.000004677661,0.0007119058,0.002095501],"genre_scores_gemma":[0.01876315,0.00002488277,0.9724668,0.001316576,0.0004472628,0.00009847631,0.00002513478,0.0001479535,0.006709743],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6211125,"threshold_uncertainty_score":0.9997597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07115953134820122,"score_gpt":0.2897249329974847,"score_spread":0.2185654016492835,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}